# Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

arXiv: https://arxiv.org/abs/2412.07808 · HTML: https://mlsanity.com/paper/2412.07808/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models](https://mlsanity.com/paper/2305.10120/) (2023)
- [Holistic Evaluation of Text-To-Image Models](https://mlsanity.com/paper/2311.04287/) (2023)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning](https://mlsanity.com/paper/2401.10371/) (2024)
- [On Copyright Risks of Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.12803/) (2023)
- [Semi-Implicit Denoising Diffusion Models (SIDDMs)](https://mlsanity.com/paper/2306.12511/) (2023)
- [Gradient Surgery for One-shot Unlearning on Generative Model](https://mlsanity.com/paper/2307.04550/) (2023)

## Built on by (most cited first, 15 of 15)

- [Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning](https://mlsanity.com/paper/2503.06339/) (2025)
- [Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2503.09446/) (2025)
- [Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations](https://mlsanity.com/paper/2501.19066/) (2025)
- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols](https://mlsanity.com/paper/2507.19894/) (2025)
- [On Surjectivity of Neural Networks: Can you elicit any behavior from your model?](https://mlsanity.com/paper/2508.19445/) (2025)
- [Probing Knowledge Holes in Unlearned LLMs](https://mlsanity.com/paper/2511.00030/) (2025)
- [Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation](https://mlsanity.com/paper/2503.16171/) (2025)
- [IMU: Influence-guided Machine Unlearning](https://mlsanity.com/paper/2508.01620/) (2025)
- [Coffee: Controllable Diffusion Fine-tuning](https://mlsanity.com/paper/2511.14113/) (2025)
- [Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM](https://mlsanity.com/paper/2604.25119/) (2026)
- [Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI](https://mlsanity.com/paper/2508.20773/) (2025)
- [You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2603.00133/) (2026)
- [Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks](https://mlsanity.com/paper/2604.21041/) (2026)
- [AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate](https://mlsanity.com/paper/2607.08337/) (2026)

## Abstract (arXiv)

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns. Driven by these concerns, machine unlearning has become crucial to effectively purge undesirable knowledge from models. While existing literature has studied various unlearning techniques, these often suffer from either poor unlearning quality or degradation in text-image alignment after unlearning, due to the competitive nature of these objectives. To address these challenges, we propose a framework that seeks an optimal model update at each unlearning iteration, ensuring monotonic improvement on both objectives. We further derive the characterization of such an update. In addition, we design procedures to strategically diversify the unlearning and remaining datasets to boost performance improvement. Our evaluation demonstrates that our method effectively removes target classes from recent diffusion-based generative models and concepts from stable diffusion models while maintaining close alignment with the models' original trained states, thus outperforming state-of-the-art baselines. Our code will be made available at https://github.com/reds-lab/Restricted_gradient_diversity_unlearning.git.